Instructions to use jefftherover/pii-layout-synth-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jefftherover/pii-layout-synth-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="jefftherover/pii-layout-synth-v2")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("jefftherover/pii-layout-synth-v2") model = AutoModelForTokenClassification.from_pretrained("jefftherover/pii-layout-synth-v2") - Notebooks
- Google Colab
- Kaggle
Training in progress, step 500
Browse files- config.json +196 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ModernBertForTokenClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 50281,
|
| 8 |
+
"classifier_activation": "gelu",
|
| 9 |
+
"classifier_bias": false,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"classifier_pooling": "mean",
|
| 12 |
+
"cls_token_id": 50281,
|
| 13 |
+
"decoder_bias": true,
|
| 14 |
+
"deterministic_flash_attn": false,
|
| 15 |
+
"dtype": "float32",
|
| 16 |
+
"embedding_dropout": 0.0,
|
| 17 |
+
"eos_token_id": 50282,
|
| 18 |
+
"global_attn_every_n_layers": 3,
|
| 19 |
+
"gradient_checkpointing": false,
|
| 20 |
+
"hidden_activation": "gelu",
|
| 21 |
+
"hidden_size": 768,
|
| 22 |
+
"id2label": {
|
| 23 |
+
"0": "O",
|
| 24 |
+
"1": "B-ACCOUNT_ID",
|
| 25 |
+
"2": "B-AGE",
|
| 26 |
+
"3": "B-AMOUNT",
|
| 27 |
+
"4": "B-CRYPTO_ID",
|
| 28 |
+
"5": "B-CUSTOMER_NAME",
|
| 29 |
+
"6": "B-DATE",
|
| 30 |
+
"7": "B-DEVICE_ID",
|
| 31 |
+
"8": "B-DOB",
|
| 32 |
+
"9": "B-EMAIL",
|
| 33 |
+
"10": "B-FINANCIAL_ID",
|
| 34 |
+
"11": "B-FIRSTNAME",
|
| 35 |
+
"12": "B-GOV_ID",
|
| 36 |
+
"13": "B-LASTNAME",
|
| 37 |
+
"14": "B-LOCAL_ADDRESS",
|
| 38 |
+
"15": "B-MIDDLENAME",
|
| 39 |
+
"16": "B-NEARBYGPSCOORDINATE",
|
| 40 |
+
"17": "B-PASSWORD",
|
| 41 |
+
"18": "B-PHONE",
|
| 42 |
+
"19": "B-PIN",
|
| 43 |
+
"20": "B-PROJECT_NAME",
|
| 44 |
+
"21": "B-REGIONAL_ADDRESS",
|
| 45 |
+
"22": "B-SECONDARY_ADDRESS",
|
| 46 |
+
"23": "B-SUFFIX",
|
| 47 |
+
"24": "B-TIME",
|
| 48 |
+
"25": "B-URL",
|
| 49 |
+
"26": "B-USERNAME",
|
| 50 |
+
"27": "B-VEHICLEVIN",
|
| 51 |
+
"28": "B-VEHICLEVRM",
|
| 52 |
+
"29": "I-ACCOUNT_ID",
|
| 53 |
+
"30": "I-AGE",
|
| 54 |
+
"31": "I-AMOUNT",
|
| 55 |
+
"32": "I-CRYPTO_ID",
|
| 56 |
+
"33": "I-CUSTOMER_NAME",
|
| 57 |
+
"34": "I-DATE",
|
| 58 |
+
"35": "I-DEVICE_ID",
|
| 59 |
+
"36": "I-DOB",
|
| 60 |
+
"37": "I-EMAIL",
|
| 61 |
+
"38": "I-FINANCIAL_ID",
|
| 62 |
+
"39": "I-FIRSTNAME",
|
| 63 |
+
"40": "I-GOV_ID",
|
| 64 |
+
"41": "I-LASTNAME",
|
| 65 |
+
"42": "I-LOCAL_ADDRESS",
|
| 66 |
+
"43": "I-MIDDLENAME",
|
| 67 |
+
"44": "I-NEARBYGPSCOORDINATE",
|
| 68 |
+
"45": "I-PASSWORD",
|
| 69 |
+
"46": "I-PHONE",
|
| 70 |
+
"47": "I-PIN",
|
| 71 |
+
"48": "I-PROJECT_NAME",
|
| 72 |
+
"49": "I-REGIONAL_ADDRESS",
|
| 73 |
+
"50": "I-SECONDARY_ADDRESS",
|
| 74 |
+
"51": "I-SUFFIX",
|
| 75 |
+
"52": "I-TIME",
|
| 76 |
+
"53": "I-URL",
|
| 77 |
+
"54": "I-USERNAME",
|
| 78 |
+
"55": "I-VEHICLEVIN",
|
| 79 |
+
"56": "I-VEHICLEVRM"
|
| 80 |
+
},
|
| 81 |
+
"initializer_cutoff_factor": 2.0,
|
| 82 |
+
"initializer_range": 0.02,
|
| 83 |
+
"intermediate_size": 1152,
|
| 84 |
+
"label2id": {
|
| 85 |
+
"B-ACCOUNT_ID": 1,
|
| 86 |
+
"B-AGE": 2,
|
| 87 |
+
"B-AMOUNT": 3,
|
| 88 |
+
"B-CRYPTO_ID": 4,
|
| 89 |
+
"B-CUSTOMER_NAME": 5,
|
| 90 |
+
"B-DATE": 6,
|
| 91 |
+
"B-DEVICE_ID": 7,
|
| 92 |
+
"B-DOB": 8,
|
| 93 |
+
"B-EMAIL": 9,
|
| 94 |
+
"B-FINANCIAL_ID": 10,
|
| 95 |
+
"B-FIRSTNAME": 11,
|
| 96 |
+
"B-GOV_ID": 12,
|
| 97 |
+
"B-LASTNAME": 13,
|
| 98 |
+
"B-LOCAL_ADDRESS": 14,
|
| 99 |
+
"B-MIDDLENAME": 15,
|
| 100 |
+
"B-NEARBYGPSCOORDINATE": 16,
|
| 101 |
+
"B-PASSWORD": 17,
|
| 102 |
+
"B-PHONE": 18,
|
| 103 |
+
"B-PIN": 19,
|
| 104 |
+
"B-PROJECT_NAME": 20,
|
| 105 |
+
"B-REGIONAL_ADDRESS": 21,
|
| 106 |
+
"B-SECONDARY_ADDRESS": 22,
|
| 107 |
+
"B-SUFFIX": 23,
|
| 108 |
+
"B-TIME": 24,
|
| 109 |
+
"B-URL": 25,
|
| 110 |
+
"B-USERNAME": 26,
|
| 111 |
+
"B-VEHICLEVIN": 27,
|
| 112 |
+
"B-VEHICLEVRM": 28,
|
| 113 |
+
"I-ACCOUNT_ID": 29,
|
| 114 |
+
"I-AGE": 30,
|
| 115 |
+
"I-AMOUNT": 31,
|
| 116 |
+
"I-CRYPTO_ID": 32,
|
| 117 |
+
"I-CUSTOMER_NAME": 33,
|
| 118 |
+
"I-DATE": 34,
|
| 119 |
+
"I-DEVICE_ID": 35,
|
| 120 |
+
"I-DOB": 36,
|
| 121 |
+
"I-EMAIL": 37,
|
| 122 |
+
"I-FINANCIAL_ID": 38,
|
| 123 |
+
"I-FIRSTNAME": 39,
|
| 124 |
+
"I-GOV_ID": 40,
|
| 125 |
+
"I-LASTNAME": 41,
|
| 126 |
+
"I-LOCAL_ADDRESS": 42,
|
| 127 |
+
"I-MIDDLENAME": 43,
|
| 128 |
+
"I-NEARBYGPSCOORDINATE": 44,
|
| 129 |
+
"I-PASSWORD": 45,
|
| 130 |
+
"I-PHONE": 46,
|
| 131 |
+
"I-PIN": 47,
|
| 132 |
+
"I-PROJECT_NAME": 48,
|
| 133 |
+
"I-REGIONAL_ADDRESS": 49,
|
| 134 |
+
"I-SECONDARY_ADDRESS": 50,
|
| 135 |
+
"I-SUFFIX": 51,
|
| 136 |
+
"I-TIME": 52,
|
| 137 |
+
"I-URL": 53,
|
| 138 |
+
"I-USERNAME": 54,
|
| 139 |
+
"I-VEHICLEVIN": 55,
|
| 140 |
+
"I-VEHICLEVRM": 56,
|
| 141 |
+
"O": 0
|
| 142 |
+
},
|
| 143 |
+
"layer_norm_eps": 1e-05,
|
| 144 |
+
"layer_types": [
|
| 145 |
+
"full_attention",
|
| 146 |
+
"sliding_attention",
|
| 147 |
+
"sliding_attention",
|
| 148 |
+
"full_attention",
|
| 149 |
+
"sliding_attention",
|
| 150 |
+
"sliding_attention",
|
| 151 |
+
"full_attention",
|
| 152 |
+
"sliding_attention",
|
| 153 |
+
"sliding_attention",
|
| 154 |
+
"full_attention",
|
| 155 |
+
"sliding_attention",
|
| 156 |
+
"sliding_attention",
|
| 157 |
+
"full_attention",
|
| 158 |
+
"sliding_attention",
|
| 159 |
+
"sliding_attention",
|
| 160 |
+
"full_attention",
|
| 161 |
+
"sliding_attention",
|
| 162 |
+
"sliding_attention",
|
| 163 |
+
"full_attention",
|
| 164 |
+
"sliding_attention",
|
| 165 |
+
"sliding_attention",
|
| 166 |
+
"full_attention"
|
| 167 |
+
],
|
| 168 |
+
"local_attention": 128,
|
| 169 |
+
"max_position_embeddings": 8192,
|
| 170 |
+
"mlp_bias": false,
|
| 171 |
+
"mlp_dropout": 0.0,
|
| 172 |
+
"model_type": "modernbert",
|
| 173 |
+
"norm_bias": false,
|
| 174 |
+
"norm_eps": 1e-05,
|
| 175 |
+
"num_attention_heads": 12,
|
| 176 |
+
"num_hidden_layers": 22,
|
| 177 |
+
"pad_token_id": 50283,
|
| 178 |
+
"position_embedding_type": "absolute",
|
| 179 |
+
"rope_parameters": {
|
| 180 |
+
"full_attention": {
|
| 181 |
+
"rope_theta": 160000.0,
|
| 182 |
+
"rope_type": "default"
|
| 183 |
+
},
|
| 184 |
+
"sliding_attention": {
|
| 185 |
+
"rope_theta": 10000.0,
|
| 186 |
+
"rope_type": "default"
|
| 187 |
+
}
|
| 188 |
+
},
|
| 189 |
+
"sep_token_id": 50282,
|
| 190 |
+
"sparse_pred_ignore_index": -100,
|
| 191 |
+
"sparse_prediction": false,
|
| 192 |
+
"tie_word_embeddings": true,
|
| 193 |
+
"transformers_version": "5.11.0",
|
| 194 |
+
"use_cache": false,
|
| 195 |
+
"vocab_size": 50368
|
| 196 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ce8e68354601b0ef3140f2bdee51fde098d252c4741096e80ea96e8f741bbca
|
| 3 |
+
size 598608972
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93e4a1fd5226245f2e3ad799563d51f8430385592a598adb09ccf80de880d36b
|
| 3 |
+
size 5265
|